Run 4. Outer Step 54. Inner Step 65.

config.json

@@ -268,24 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5579616,
-    5579620,
-    5579622,
-    5579624,
-    5579625,
-    5579626,
-    5579626,
-    5579628,
-    5579631,
-    5579633,
-    5579635
+    5579638,
+    5579640,
+    5579642,
+    5579645,
+    5579648
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 64,
+  "inner_step": 65,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2613ff6768513d3885f0ddf5bc1bcb111628e9b39023ddc2b242750b50e742
+oid sha256:c81ab456500ffe674f116a643501ccd9b4d8b5e0aacc236cdd8088d6d79fa062
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94df99a2893cd2f68ab26c4df1c88a6c174ad5f9c0a4a6a1f051d00d38ba1762
+oid sha256:699df9536ad7a17668422be3597c18a6c2b26365b10f25ce72c2ea2512c69315
 size 4040701744